CN105574182A - News recommendation method and device as well as device for news recommendation - Google Patents
News recommendation method and device as well as device for news recommendation Download PDFInfo
- Publication number
- CN105574182A CN105574182A CN201510971864.2A CN201510971864A CN105574182A CN 105574182 A CN105574182 A CN 105574182A CN 201510971864 A CN201510971864 A CN 201510971864A CN 105574182 A CN105574182 A CN 105574182A
- Authority
- CN
- China
- Prior art keywords
- news
- refresh requests
- current time
- scene
- time scene
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Abstract
The embodiment of the invention provides a news recommendation method and device as well as a device for news recommendation. The method specifically comprises: receiving a news refreshing requirement; determining a current time scene corresponding to the refreshing requirement based on corresponding current time of the refreshing requirement and/or a time interval between the refreshing requirement and a previous refreshing requirement; obtaining the news category proportion corresponding to the current time scene, and selecting news of the corresponding news category as target news; outputting the target news. The embodiment provided by the invention can improve news recommendation accuracy.
Description
Technical field
The present invention relates to technical field of information processing, particularly relate to a kind of news recommend method, a kind of recommendation apparatus and a kind of device recommended for news.
Background technology
Along with the fast development of internet, web database technology constantly increases, while offering convenience to network user's obtaining information, also result in problem of information overload, how in the data of magnanimity, fast and effeciently Search and Orientation becomes the developing outstanding problem of current internet to the information of needs.
In order to solve the problem, most news website can select top news on homepage or channel homepage, and be placed on destination locations of relatively waking up, to help user to find interested content, thus can effectively help user to find the resource of needs quickly and accurately.
In existing scheme, a kind of client obtains top-line flow process, specifically can comprise the steps:
Step 1, when receiving the refreshing instruction from user, user end to server send refresh requests;
Step 2, server, after receiving refresh requests, select the news of different news category as top news according to fixed proportion;
Above-mentioned top news is pushed to client by step 3, server;
Above-mentioned top news is showed user by step 4, client.
Wherein, above-mentioned fixed proportion refers to that the ratio of different news category is fixed, and the such as ratio of news category 1 and news category 2 is 50% etc.But above-mentionedly select dissimilar news as top-line mode according to fixed proportion all the time, easily cause recommending by the news that other channels have been seen to user, this will affect the accuracy of news recommendation.Such as, suppose to recommend to user at night according to above-mentioned fixed proportion, 5 news of news category 1 that the top news of recommending comprises and 5 news of news category 2, and wherein 3 news of news category 1 may have been seen by other channels such as TV or computer at the other times on the same day by user, then 3 news of news category 1 will be no longer the news needed for user.
Summary of the invention
In view of the above problems, propose the embodiment of the present invention to provide a kind of overcoming the problems referred to above or the news recommend method solved the problem at least in part, news recommendation apparatus and the device for news recommendation, the accuracy that news is recommended can be improved.
In order to solve the problem, the invention discloses a kind of news recommend method, comprising:
Receive the refresh requests for news;
The current time corresponding according to described refresh requests and/or the time interval between described refresh requests and a front refresh requests, determine the current time scene that described refresh requests is corresponding;
Obtain the news category ratio that described current time scene is corresponding, select the news of corresponding news category as targeted news;
Export described targeted news.
Alternatively, the step of the news category ratio that described acquisition described current time scene is corresponding, comprising:
According to described current time scene, search in the mapping relations between the preset time scene set up in advance and preset news category ratio, to obtain news category ratio corresponding to described current time scene; Wherein, described mapping relations are obtain according to the historical behavior data of user under preset time scene; Or
To the historical behavior data analysis of user under current time scene, to obtain news category ratio corresponding to described current time scene.
Alternatively, the mapping relations between preset time scene and preset news category ratio are set up as follows:
To the historical behavior data analysis of user under preset time scene, to obtain user's attention rate for news category under above-mentioned preset time scene;
According to user for the attention rate of news category, determine the ratio between at least two kinds of preset news category, as the preset news category ratio that described preset time scene is corresponding.
Alternatively, the described current time corresponding according to described refresh requests and/or the time interval between described refresh requests and a front refresh requests, determine the step of the current time scene that described refresh requests is corresponding, comprising:
When the current time that described refresh requests is corresponding is positioned at very first time interval, current time scene corresponding for described refresh requests is defined as very first time scene; Or
When the current time that described refresh requests is corresponding is positioned at the second time interval, current time scene corresponding for described refresh requests is defined as the second Novel Temporal Scenario; Or
When the current time that described refresh requests is corresponding is positioned at the 3rd time interval and the described time interval exceeds interval threshold, current time scene corresponding for described refresh requests is defined as the 3rd Novel Temporal Scenario; Or
When the current time that described refresh requests is corresponding is positioned at the 3rd time interval and the described time interval does not exceed interval threshold, current time scene corresponding for described refresh requests is defined as the 4th Novel Temporal Scenario.
Alternatively, before the described targeted news of described output, described method also comprises:
Described targeted news is carried out interting sequence, to obtain sorted targeted news;
The then step of the described targeted news of described output, comprising: exported by sorted targeted news.
Alternatively, described news category comprises: first category and the second classification;
Wherein, described first category is the news category that attention rate is the highest under very first time scene, and described second classification is the news category that attention rate is the highest under the second Novel Temporal Scenario.
Alternatively, described news category also comprises: the 3rd classification, and wherein, described 3rd classification is different with described second classification from described first category.
Alternatively, described method is applied to client, and described refresh requests is the refresh requests that user triggers, and the step of the described targeted news of described output, comprising:
Described targeted news is represented to user.
Alternatively, described method is applied to server, and described refresh requests is the refresh requests from client, and the step of the described targeted news of described output, comprising:
To targeted news described in client push.
On the other hand, the invention discloses a kind of news recommendation apparatus, comprising:
Receiver module, for receiving the refresh requests for news;
Determination module, for according to current time corresponding to described refresh requests and/or the time interval between described refresh requests and a front refresh requests, determines the current time scene that described refresh requests is corresponding;
Acquisition module, for obtaining news category ratio corresponding to described current time scene;
Select module, for according to news category ratio corresponding to described current time scene, select the news of corresponding news category as targeted news; And
Output module, for exporting described targeted news.
Again on the one hand, the invention discloses a kind of device recommended for news, include storer, and one or more than one program, one of them or more than one program are stored in storer, and are configured to perform described more than one or one routine package containing the instruction for carrying out following operation by more than one or one processor:
Receive the refresh requests for news;
The current time corresponding according to described refresh requests and/or the time interval between described refresh requests and a front refresh requests, determine the current time scene that described refresh requests is corresponding;
Obtain the news category ratio that described current time scene is corresponding, select the news of corresponding news category as targeted news;
Export described targeted news.
Alternatively, described processor is also for performing described more than one or one routine package containing the instruction for carrying out following operation:
According to described current time scene, search in the mapping relations between the preset time scene set up in advance and preset news category ratio, to obtain news category ratio corresponding to described current time scene; Wherein, described mapping relations are obtain according to the historical behavior data of user under preset time scene; Or
To the historical behavior data analysis of user under current time scene, to obtain news category ratio corresponding to described current time scene.
Alternatively, described processor is also for performing described more than one or one routine package containing the instruction for carrying out following operation:
When the current time that described refresh requests is corresponding is positioned at very first time interval, current time scene corresponding for described refresh requests is defined as very first time scene; Or
When the current time that described refresh requests is corresponding is positioned at the second time interval, current time scene corresponding for described refresh requests is defined as the second Novel Temporal Scenario; Or
When the current time that described refresh requests is corresponding is positioned at the 3rd time interval and the described time interval exceeds interval threshold, current time scene corresponding for described refresh requests is defined as the 3rd Novel Temporal Scenario; Or
When the current time that described refresh requests is corresponding is positioned at the 3rd time interval and the described time interval does not exceed interval threshold, current time scene corresponding for described refresh requests is defined as the 4th Novel Temporal Scenario.
Alternatively, described processor is also for performing described more than one or one routine package containing the instruction for carrying out following operation:
Described targeted news is carried out interting sequence, to obtain sorted targeted news;
Sorted targeted news is exported.
The embodiment of the present invention comprises following advantage:
The embodiment of the present invention is according to current time corresponding to refresh requests and/or the time interval between described refresh requests and a front refresh requests, user is corresponded to different Novel Temporal Scenarios to browsing of news, and adopt different news category ratios for different Novel Temporal Scenarios, and then recommend the targeted news corresponding to above-mentioned news category ratio to user; Because the news category ratio that current time scene is corresponding can agree with the information requirement tendency of user under current time scene, therefore the embodiment of the present invention can improve the accuracy that news is recommended.
Suppose that current time scene is scene in evening, then in the news of recommending under scene this evening, ratio shared by the news of current events classification can be less than the first predetermined threshold value, ratio shared by the news of personalization categories can be greater than the second predetermined threshold value, this first predetermined threshold value can be 20%, and this second predetermined threshold value can be 60%, like this, when user has seen the current events classification news of being correlated with from TV or computer, can avoid recommending too much redundant information to user; And the personalization categories news of larger proportion can attract user preferably, the information requirement tendency of user under current time scene also namely can be agreed with.
Accompanying drawing explanation
Fig. 1 is the schematic diagram of the applied environment of a kind of news recommend method of the present invention;
Fig. 2 is the flow chart of steps of a kind of news recommend method embodiment one of the present invention;
Fig. 3 is the flow chart of steps of a kind of news recommend method embodiment two of the present invention;
Fig. 4 is the flow chart of steps of a kind of news recommend method embodiment three of the present invention;
Fig. 5 is the structured flowchart of a kind of news recommendation apparatus embodiment of the present invention;
Fig. 6 is the block diagram of a kind of device 800 for news recommendation of the present invention; And
Fig. 7 is the structural representation of a kind of server of the present invention.
Embodiment
For enabling above-mentioned purpose of the present invention, feature and advantage become apparent more, and below in conjunction with the drawings and specific embodiments, the present invention is further detailed explanation.
Existing scheme selects different classes of news as top-line mode according to fixed proportion, easily causes recommending by news that other channels have been seen to user.Such as, when recommending many current events classification news to user at night, this user possible has seen the news of being correlated with from TV or computer, and this have impact on the accuracy that news is recommended.
And inventor herein finds after deliberation, the information requirement of user tendency is often relevant with Novel Temporal Scenario, and also, by the collection of the historical behavior data of user and accumulation and analysis, the information requirement tendency under special time scene is often regular to be followed; Like this, the rule that can obtain between Novel Temporal Scenario and news category ratio according to the historical behavior data analysis of user, and recommend news to user according to the news category ratio of agreeing with current information demand tendency, thus the accuracy that can improve that news recommends.
Such as, by analyze user for the navigation patterns data of news, following rule can be obtained: in the morning with the long time interval after read news first time, user compares the news tending to browse current events classification; And at night with in the short time interval, user tends to the news browsing personalization categories.Therefore, user can be corresponded to different Novel Temporal Scenarios to browsing of news according to moment different in one day and/or the time interval between described refresh requests from a front refresh requests by the embodiment of the present invention, and adopt different news category ratios for different Novel Temporal Scenarios, such as, in the news of recommending at night, ratio shared by the news of current events classification can be less than the first predetermined threshold value, ratio shared by the news of personalization categories can be greater than the second predetermined threshold value, this first predetermined threshold value can be 20%, this second predetermined threshold value can be 60%, like this, when user has seen the current events classification news of being correlated with from TV or computer, can avoid recommending too much redundant information to user, and the personalization categories news of larger proportion can attract user preferably, also namely can agree with the information requirement tendency of user under current time scene, thus improve the accuracy of news recommendation.
The embodiment of the present invention can be applied in the applied environment such as news website, news APP (application program, Application), to improve the accuracy that news is recommended; In addition, the embodiment of the present invention can be applied in the recommendation such as top news, homepage scene, is appreciated that the embodiment of the present invention is not limited for concrete applied environment and concrete recommendation scene.
The news recommend method that the embodiment of the present invention provides can be applicable in the applied environment shown in Fig. 1, as shown in Figure 1, client 100 and server 200 are arranged in wired or wireless network, and by this wired or wireless network, client 100 and server 200 carry out data interaction.
Particularly, client 100 when receiving the refreshing instruction from user, can send refresh requests to server;
Server 200 is after receiving above-mentioned refresh requests, the current time corresponding according to above-mentioned refresh requests and/or the time interval between described refresh requests and a front refresh requests, determine the current time scene that described refresh requests is corresponding, and obtain news category ratio corresponding to described current time scene, select the news of corresponding news category as targeted news, and then export above-mentioned targeted news to client 100;
Client 100 reception server 200 send for targeted news after, above-mentioned targeted news can be shown to user and check.
Wherein, client 100 may operate on information equipment, above-mentioned information equipment specifically comprises but does not limit: smart mobile phone, panel computer, E-book reader, MP3 (dynamic image expert compression standard audio frequency aspect 3, MovingPictureExpertsGroupAudioLayerIII) player, MP4 (dynamic image expert compression standard audio frequency aspect 4, MovingPictureExpertsGroupAudioLayerIV) player, pocket computer on knee, vehicle-mounted computer, desk-top computer, Set Top Box, intelligent TV set, wearable device etc.
Embodiment of the method one
With reference to Fig. 2, show the flow chart of steps of a kind of news recommend method embodiment one of the present invention, specifically can comprise the steps:
Step 201, receive refresh requests for news;
The embodiment of the present invention can be applied to client or server;
Wherein, when being applied to client, above-mentioned refresh requests is the refresh requests that user triggers, then client by performing step 202-step 204 to obtain targeted news corresponding to above-mentioned refresh requests, and can represent described targeted news by information equipment to user;
When being applied to server, above-mentioned refresh requests can be the refresh requests from client, then server can pass through to perform step 202-step 204 to obtain targeted news corresponding to above-mentioned refresh requests, and to target resource described in client push.
Step 202, according to current time corresponding to described refresh requests and/or the time interval between described refresh requests and a front refresh requests, determine the current time scene that described refresh requests is corresponding;
The time interval between described refresh requests with a front refresh requests can be used for the current time T representing that current refresh requests is corresponding
nthe time T corresponding with a front refresh requests
n-1between the time interval: T
n-T
n-1.
The embodiment of the present invention can provide: the described current time corresponding according to described refresh requests and/or the time interval between described refresh requests and a front refresh requests, determine the following technical scheme of the current time scene that described refresh requests is corresponding:
Technical scheme A1,
In technical scheme A1, when the current time that described refresh requests is corresponding is positioned at very first time interval, current time scene corresponding for described refresh requests can be defined as very first time scene.
Technical scheme A2,
In technical scheme A2, when the current time that described refresh requests is corresponding is positioned at the second time interval, current time scene corresponding for described refresh requests can be defined as the second Novel Temporal Scenario.
The similarity of very first time scene and the second Novel Temporal Scenario is, the two can be determined by very first time interval or the second time interval, and also, in very first time interval or the second time interval, the information requirement tendency of user is fixing substantially.
Therefore, in actual applications, the mapping relations between very first time scene and very first time interval can be set up in advance.Such as, in a kind of application example 1 of the present invention, very first time scene can be scene in morning, then the very first time interval of its correspondence can be (6:00,10:00).In the morning in scene, most of user is more prone to wish to understand the current events hot news occurred the previous day, therefore, although the information requirement tendency of user specifically can comprise: current events classification and personalization categories, but, in the morning in scene, user is far longer than user be inclined to for the information requirement of personalization categories for the information requirement tendency of current events classification, and this information requirement is inclined to and is fixed often in very first time interval corresponding to scene in the morning.
In actual applications, the mapping relations between the second Novel Temporal Scenario and the second time interval can be set up in advance.Such as, in a kind of application example 2 of the present invention, the second Novel Temporal Scenario can be scene in evening, then the second time interval of its correspondence can be (19:00, T
m), wherein, T
mthe corresponding time can be less than 24:00, and namely the second time interval belongs to a period of time on the same day, T
malso can be more than or equal to 0:00 and be less than 6:00, namely the second time interval belongs to one period of continuous time in adjacent two days, such as, and T
mwhen getting 3:00, the second time interval be 19:00 on the same day after to the continuous time section of morning between 3:00 of second day.The embodiment of the present invention is not limited for the left end point of above-mentioned second time interval or concrete time corresponding to right endpoint.At night in scene, most of user is more prone to the news of watching personal like, and as women likes the news of the aspect such as amusement, video display usually, and the male sex likes the news etc. of the aspect such as military affairs, physical culture usually; Therefore, although the information requirement tendency of user specifically can comprise: current events classification and personalization categories, but, at night in scene, user is far longer than user be inclined to for the information requirement of current events classification for the information requirement tendency of personalization categories, and this information requirement is inclined to and is fixed often in the second time interval corresponding to scene at night.
Technical scheme A3,
In technical scheme A3, when the current time that described refresh requests is corresponding is positioned at the 3rd time interval and the described time interval exceeds interval threshold, current time scene corresponding for described refresh requests can be defined as the 3rd Novel Temporal Scenario.
Technical scheme A4,
In technical scheme A4, when the current time that described refresh requests is corresponding is positioned at the 3rd time interval and the described time interval does not exceed interval threshold, current time scene corresponding for described refresh requests is defined as the 4th Novel Temporal Scenario.
3rd Novel Temporal Scenario or the 4th Novel Temporal Scenario are relative to a difference of very first time scene and the second Novel Temporal Scenario, and the 3rd Novel Temporal Scenario or the 4th Novel Temporal Scenario can be determined jointly by the 3rd time interval and the time interval.Also be, in the 3rd time interval, the information requirement tendency of user is variable, particularly, when the time interval does not exceed interval threshold, tendency corresponding to corresponding 4th Novel Temporal Scenario is inclined in the information requirement of user, and when the time interval exceeds interval threshold, tendency corresponding to corresponding 3rd Novel Temporal Scenario is inclined in the information requirement of user.
Above-mentioned interval threshold can be used for the threshold value representing the information requirement tendency change affecting user in the 3rd time interval, it can for the numerical value obtained historical behavior data analysis, also the numerical value can determined according to practical application request for those skilled in the art, the embodiment of the present invention is not limited for the concrete numerical value of above-mentioned interval threshold.
In a kind of application example 3 of the present invention, the 3rd time interval can be with second time interval different interval interval from the very first time, and as (10:00,19:00), above-mentioned interval threshold can be 3 hours.Wherein, when interval greater than interval threshold, user sees that news is more prone to wish to understand during this period of time the current events hot news occurred, and is also corresponding 3rd Novel Temporal Scenario of information requirement tendency of user; And when the time interval does not exceed interval threshold, user is more prone to browse personalized relevant content, also namely corresponding 4th Novel Temporal Scenario is inclined in the information requirement of user.
Be appreciated that, shown in above-mentioned very first time interval, the second time interval and the 3rd time interval, open interval just exemplarily, and in fact those skilled in the art can adopt closed interval according to practical application request, half-open interval describes interval, the second time interval of the above-mentioned very first time and the 3rd time interval.
In a kind of application example of the present invention, above-mentioned 3rd Novel Temporal Scenario specifically can comprise: daytime closely-spaced scene, above-mentioned 4th Novel Temporal Scenario specifically can comprise: daytime large-spacing scene; Above-mentioned daytime closely-spaced scene and daytime large-spacing scene all can be determined by the 3rd time interval and interval threshold; Wherein, when the current time that described refresh requests is corresponding is positioned at the 3rd time interval and the described time interval does not exceed interval threshold, current time scene corresponding for described refresh requests can be defined as closely-spaced scene on daytime; When the current time that described refresh requests is corresponding is positioned at the 3rd time interval and the described time interval exceeds interval threshold, current time scene corresponding for described refresh requests can be defined as large-spacing scene on daytime.
In addition, above-mentioned very first time scene, second Novel Temporal Scenario, the interval threshold of the 3rd Novel Temporal Scenario and the 4th Novel Temporal Scenario and corresponding time interval and correspondence thereof is also just as alternatives, in fact, those skilled in the art can be according to the actual requirements, concrete Novel Temporal Scenario is determined according to information requirement tendency, and adopt corresponding time interval and the interval threshold of correspondence thereof according to concrete Novel Temporal Scenario and information requirement tendency corresponding to Novel Temporal Scenario, the embodiment of the present invention is not limited for concrete Novel Temporal Scenario and corresponding concrete time interval thereof and/or interval threshold.
Step 203, obtain news category ratio corresponding to described current time scene;
In a kind of embodiment of the embodiment of the present invention, according to historical behavior data corresponding to Novel Temporal Scenario, the news category ratio that described current time scene is corresponding can be obtained.Wherein, the user that historical behavior data corresponding to Novel Temporal Scenario are relevant specifically can comprise: at least one in the user of the good friend user of active user, active user, the user of active user place group, active user place family and all users, wherein, active user can refer to the user that current refresh requests is corresponding, active user place group can for agreeing with the group of the hobby of active user, as " basket ball fan group ", " programming fever person group ", " constellation be correlated with group " etc.Also be, can by analyzing active user, the user with active user with identical hobby or historical behavior data corresponding to all users, to obtain for active user, with active user, to there is the user of identical hobby or the news category ratio of all users.
In addition, the historical behavior data that Novel Temporal Scenario is corresponding can across application program or inter-network station, also be, the historical behavior data that Novel Temporal Scenario is corresponding not only can comprise: user passes through the historical behavior data of news program or news website generation in this Novel Temporal Scenario, can also comprise: user passes through the historical behavior data of other application programs or the generation of other websites in this Novel Temporal Scenario, here other application programs specifically can comprise: other application programs run on the information equipment of user, as instant messaging program, audio-visual class method, input method procedure etc., here other websites specifically can comprise: other websites run on the information equipment of user, as search engine etc., particularly, the corresponding historical behavior data that user produced by website can be gathered by browser.
And, the behavior that above-mentioned historical behavior data are relevant specifically can comprise: at least one in inputting, browse, search for, recommend, share, forward and commenting on, be appreciated that the embodiment of the present invention is not limited for the behavior that above-mentioned historical behavior data are relevant.
In addition, it should be noted that, the behavioral data that above-mentioned historical behavior data can produce within a nearest preset time period for user, wherein, the length of above-mentioned preset time period can be one week, one month, season etc., and the embodiment of the present invention is not limited for the length of concrete preset time period.
To sum up, the embodiment of the present invention is correlated with for the historical behavior data that Novel Temporal Scenario is corresponding particular user, specific procedure or website or concrete behavior or concrete time period are not limited.
The embodiment of the present invention can provide the following technical scheme obtaining news category ratio corresponding to described current time scene:
Technical scheme B1
Technical scheme B1 according to described current time scene, can search in the mapping relations between the preset time scene set up in advance and preset news category ratio, to obtain news category ratio corresponding to described current time scene; Wherein, described mapping relations can for obtaining according to the historical behavior data of user under preset time scene.Technical scheme B1 obtains news category ratio corresponding to current time scene by searching mapping relations, can improve the acquisition efficiency of news category ratio corresponding to current time scene.
In a kind of embodiment of the present invention, the mapping relations between preset time scene and preset news category ratio can be set up as follows:
Step S1, to the historical behavior data analysis of user under preset time scene, to obtain user's attention rate for news category under above-mentioned preset time scene;
Step S2, foundation user, for the attention rate of news category, determine the ratio between at least two kinds of news category, as the preset news category ratio that described preset time scene is corresponding.
In actual applications, preset time scene specifically can comprise: the Novel Temporal Scenario that above-mentioned very first time scene, the second Novel Temporal Scenario and the 3rd Novel Temporal Scenario etc. are determined according to practical application request.
In a kind of embodiment of the present invention, suppose to record in historical behavior data the information such as the behavior of news, news category and correspondence, then can add up the first quantity of the corresponding behavior of often kind of news category, using as above-mentioned attention rate; Further, according to the ratio of the first quantity in the quantity of all news category of often kind of news category, the preset news category ratio that described preset time scene is corresponding can also be determined.
In another kind of embodiment of the present invention, suppose the information such as the behavior recording webpage and correspondence in historical behavior data, then can add up the second quantity of the corresponding behavior of often kind of webpage, and according to above-mentioned second quantity and the mapping relations between webpage and news category, determine the attention rate that often kind of news category is corresponding.Be appreciated that the embodiment of the present invention is not limited for obtaining the detailed process of user for the attention rate of news category under above-mentioned preset time scene by analysis.
In a kind of embodiment of the embodiment of the present invention, news category ratio can show as: the ratio in all targeted news shared by each preset news category or the ratio between preset news category.
In a kind of embodiment of the present invention, described preset news category specifically can comprise: first category and the second classification; Wherein, described first category is the news category that attention rate is the highest under very first time scene, and described second classification is the news category that attention rate is the highest under the second Novel Temporal Scenario.Such as, first category can be the current events classification that attention rate is the highest under scene in the morning, and the second classification can be the personalization categories that attention rate is the highest under scene at night.Wherein, above-mentioned current events classification specifically can comprise: the subclass such as political situation of the time class, social class, above-mentioned personalization categories specifically can comprise: the subclass such as amusement class, military class, football class, basketball class, internet-class, automotive-type, and subclass here can be the subclass corresponding to the space of a whole page of news website or news program; Further, in the morning under scene, the ratio between current events classification and personalization categories can be 4:1,3:1 etc.; At night under scene, the ratio between current events classification and personalization categories can be 1:4,1:3 etc.
In another kind of embodiment of the present invention, in order to increase the diversity of news, except first category and the second classification, described preset news category can also comprise: the 3rd classification, wherein, described 3rd classification can be different with described second classification from described first category.Such as, the personalization categories of a user specifically comprises amusement, football and internet etc., then except selecting the news of current events classification and personalization categories, several news can also be selected from the news of the non-current events impersonal theory classifications such as military and automobile, using as targeted news.
In a kind of embodiment of the present invention, in the attention rate of foundation user for news category, determine in the process of the ratio between at least two kinds of preset news category, the ratio that single preset news category is shared in all targeted news can be controlled, to obtain final news category ratio.Such as, at night under scene, ratio shared by the news of current events classification can be less than the first predetermined threshold value, ratio shared by the news of personalization categories can be greater than the second predetermined threshold value, this first predetermined threshold value can be 20%, this second predetermined threshold value can be 60%, then the ratio shared by news of non-current events impersonal theory classification can be 100%-20%-60%=20%.
It should be noted that, in the embodiment of the present invention, that personalization categories can obtain for the historical behavior data by analyzing user, that attention rate is the highest at least one classification.With reference to foregoing teachings, the historical behavior data of user can across application program or inter-network station, also be, the historical behavior data that user is produced by various application program or website users such as input method procedure, search engine, news website, social network sites, instant messaging programs (as QQ, micro-letter) can be collected, and to collected historical behavior data analysis, to obtain the personalization categories of user, the embodiment of the present invention is not limited for the concrete acquisition process of the personalization categories of user.
In addition, it should be noted that, above-mentioned first category is current events classification, second classification is that personalization categories is just as optional embodiment of the present invention, in fact, those skilled in the art can also adopt other classifications as above-mentioned first category or the second classification according to practical application request, such as, above-mentioned first category or the second classification can subclass corresponding to the space of a whole page of news website or news program, or, above-mentioned first category or the second classification can also for the classifications etc. determined according to practical application request, be appreciated that, the embodiment of the present invention is not limited for concrete first category or the second classification.
Technical scheme B2
Technical scheme B2 can to the historical behavior data analysis of user under current time scene, to obtain news category ratio corresponding to described current time scene.
Obtain news category ratio corresponding to current time scene relative to technical scheme B1 by searching mapping relations, technical scheme B2 can by on-line analysis to obtain news category ratio corresponding to current time scene.Such as, in a kind of application example of the present invention, current time scene is scene in evening, active user is 50 the quantity of on average watching the news of personalization categories evening in scene every day of nearest one month, the quantity of the news of viewing current events classification is 5, then can using 50:5 as the ratio between personalization categories and current events classification, or, can also using the ratio near 50:5 as the ratio between personalization categories and current events classification.
Be appreciated that, the above-mentioned historical behavior data corresponding according to Novel Temporal Scenario, determine that the technical scheme B1-technical scheme B2 of the news category ratio that described current time scene is corresponding is just as embodiment, and be not understood to application of the present invention restriction, also be, the embodiment of the present invention, for according to historical behavior data corresponding to Novel Temporal Scenario, determines that the concrete technical scheme of the news category ratio that described current time scene is corresponding is not limited.
Step 204, according to news category ratio corresponding to described current time scene, select the news of corresponding news category as targeted news;
Step 205, export described targeted news.
To sum up, the embodiment of the present invention is according to current time corresponding to refresh requests and/or the time interval between described refresh requests and a front refresh requests, user is corresponded to different Novel Temporal Scenarios to browsing of news, and adopt different news category ratios for different Novel Temporal Scenarios, and then recommend the targeted news corresponding to above-mentioned news category ratio to user; Due to the information requirement tendency of user under current time scene can be agreed with, therefore, it is possible to improve the accuracy of news recommendation.
Suppose that current time scene is scene in evening, then in the news of recommending under scene this evening, ratio shared by the news of current events classification can be less than the first predetermined threshold value, ratio shared by the news of personalization categories can be greater than the second predetermined threshold value, this first predetermined threshold value can be 20%, and this second predetermined threshold value can be 60%, like this, when user has seen the current events classification news of being correlated with from TV or computer, can avoid recommending too much redundant information to user; And the personalization categories news of larger proportion can attract user preferably, the information requirement tendency of user under current time scene also namely can be agreed with.
Embodiment of the method two
With reference to Fig. 3, show the flow chart of steps of a kind of news recommend method embodiment two of the present invention, specifically can comprise the steps:
Step 301, receive refresh requests for news;
Step 302, according to current time corresponding to described refresh requests and/or the time interval between described refresh requests and a front refresh requests, determine the current time scene that described refresh requests is corresponding;
Step 303, obtain news category ratio corresponding to described current time scene;
Step 304, according to news category ratio corresponding to described current time scene, select the news of corresponding news category as targeted news;
Step 305, to described targeted news carry out intert sequence, to obtain sorted targeted news;
Step 306, sorted targeted news to be exported.
The present embodiment is the embodiment of embodiment of the method one, and it is on the basis of embodiment of the method one, can also carry out interting sequence, and exported by sorted targeted news described targeted news.
For the information equipments such as mobile phone, the finiteness of its screen size causes to show all targeted news on current screen, and above-mentioned interspersed sequence can be avoided showing to user in current screen is all the news of same news category, the news of the identical news category of discontinuous appearance many sections also namely can be guaranteed.
In a kind of application example of the present invention, above-mentioned targeted news specifically can comprise: 2 news of 6 news of current events classification, 2 news of personalization categories and non-current events impersonal theory classification, then above-mentioned interspersed sequence can insert the news of 1 personalization categories and the news of 1 non-current events impersonal theory classification after the news every 2 current events classifications, respectively.With reference to table 1, show the example of the targeted news after a kind of interspersed sequence of the embodiment of the present invention.Be appreciated that, table 1 is just as interting a kind of example sorted, in fact, those skilled in the art can also adopt other to intert according to practical application request and sort, such as, after the news every 1 current events classification, respectively, insert the news of 1 personalization categories and the news etc. of 1 non-current events impersonal theory classification, the embodiment of the present invention is not limited for concrete interspersed sequencer procedure.
Table 1
| The news of current events classification |
| The news of current events classification |
| The news of personalization categories |
| The news of non-current events impersonal theory classification |
| The news of current events classification |
| The news of current events classification |
| The news of personalization categories |
| The news of non-current events impersonal theory classification |
| The news of current events classification |
| The news of current events classification |
Embodiment of the method three
With reference to Fig. 4, show the flow chart of steps of a kind of news recommend method embodiment three of the present invention, be applied to server, specifically can comprise the steps:
Step 401, server receive the refresh requests for news from client;
Step 402, server determine the personalization categories of user according to user ID;
Step 403, server, according to current time corresponding to described refresh requests and/or the time interval between described refresh requests and a front refresh requests, determine the current time scene that described refresh requests is corresponding;
The historical behavior data that step 404, server foundation Novel Temporal Scenario is corresponding, obtain the news category ratio that described current time scene is corresponding;
Step 405, server, according to news category ratio corresponding to described current time scene, select the news of corresponding news category as targeted news;
Step 406, server carry out interting sequence, to obtain sorted targeted news to described targeted news;
Step 407, server are to the sorted targeted news of client push.
Wherein, above-mentioned user ID (mark, Identity) can be used for representing the account of user in news website or news program, and also can be used for the device identification representing that user is corresponding, the embodiment of the present invention is not limited for concrete user ID.
In a kind of embodiment of the present invention, above-mentioned Novel Temporal Scenario specifically can comprise: morning scene, evening scene, daytime closely-spaced scene and daytime large-spacing scene; Wherein, morning scene and news category ratio corresponding to large-spacing scene on daytime in, the ratio of current events classification is greater than the ratio of personalization categories, evening scene and news category ratio corresponding to closely-spaced scene on daytime in, the ratio of current events classification is less than the ratio of personalization categories.
In a kind of application example of the present invention, when the news that user A eight at night is opened in mobile phone reads application, client can send refresh requests to service end, after service end receives this refresh requests, first read the customized information of this user A, find that the personalization categories of this user specifically can comprise: amusement, military affairs and internet etc., then, service end judges that current time is evening, the ratio of current events classification then can be adopted to be less than news category ratio corresponding to the ratio of personalization categories, suppose current events classification, the ratio of personalization categories and non-military impersonal theory classification is respectively: 1:3:1, if the words of propelling movement 10 news altogether, then server can from amusement, 6 news are chosen in the personalization categories such as military affairs and internet, 2 news are chosen from the news of current events classification, 2 news are chosen from non-current events impersonal theory classification, and the mixing of elect 10 news is interted be pushed to client together, after client receives the targeted news that server sends, this targeted news can be presented to user and read.
Can find out, in the news of recommending under scene this evening, the ratio shared by the news of current events classification is less, like this, when user has seen the current events classification news of being correlated with from TV or computer, can avoid recommending too much redundant information to user; And the personalization categories news of larger proportion can attract user preferably, the information requirement tendency of user under current time scene also namely can be agreed with.
It should be noted that, for embodiment of the method, in order to simple description, therefore it is all expressed as a series of combination of actions, but those skilled in the art should know, the embodiment of the present invention is not by the restriction of described sequence of movement, because according to the embodiment of the present invention, some step can adopt other orders or carry out simultaneously.Secondly, those skilled in the art also should know, the embodiment described in instructions all belongs to preferred embodiment, and involved action might not be that the embodiment of the present invention is necessary.
Device embodiment
With reference to Fig. 5, show the structured flowchart of a kind of recommendation apparatus embodiment of the present invention, specifically can comprise as lower module:
Receiver module 501, for receiving the refresh requests for news;
Determination module 502, for according to current time corresponding to described refresh requests and/or the time interval between described refresh requests and a front refresh requests, determines the current time scene that described refresh requests is corresponding;
Acquisition module 503, for obtaining news category ratio corresponding to described current time scene;
Select module 504, for according to news category ratio corresponding to described current time scene, select the news of corresponding news category as targeted news; And
Output module 505, for exporting described targeted news.
In a kind of embodiment of the present invention, described second determination module 503, specifically can comprise:
Search submodule, for according to described current time scene, search in the mapping relations between the preset time scene set up in advance and preset news category ratio, to obtain news category ratio corresponding to described current time scene; Wherein, described mapping relations are obtain according to the historical behavior data of user under preset time scene; Or
First analyzes submodule, for the historical behavior data analysis of user under current time scene, to obtain news category ratio corresponding to described current time scene.
In another kind of embodiment of the present invention, described device can also comprise:
Set up module, for setting up the mapping relations between preset time scene and preset news category ratio:
Wherein, describedly set up module, specifically can comprise:
Second analyzes submodule, for the historical behavior data analysis of user under preset time scene, to obtain user's attention rate for news category under above-mentioned preset time scene;
First determines submodule, for foundation user for the attention rate of news category, determines the ratio between at least two kinds of preset news category, as the preset news category ratio that described preset time scene is corresponding.
In another embodiment of the present invention, described first determination module 502, specifically can comprise:
Second determines submodule, when being positioned at very first time interval for the current time corresponding in described refresh requests, current time scene corresponding for described refresh requests is defined as very first time scene; Or
3rd determines submodule, when being positioned at the second time interval for the current time corresponding in described refresh requests, current time scene corresponding for described refresh requests is defined as the second Novel Temporal Scenario; Or
4th determines submodule, be positioned at the 3rd time interval for the current time corresponding in described refresh requests and the described time interval exceeds interval threshold time, current time scene corresponding for described refresh requests is defined as the 3rd Novel Temporal Scenario; Or
5th determines submodule, be positioned at the 3rd time interval for the current time corresponding in described refresh requests and the described time interval does not exceed interval threshold time, current time scene corresponding for described refresh requests is defined as the 4th Novel Temporal Scenario.
In another embodiment of the present invention, described device can also comprise:
Order module, for carrying out interting sequence to described targeted news, to obtain sorted targeted news;
Then described output module 505, specifically can comprise: for the output sub-module exported by sorted targeted news.
In a kind of embodiment of the present invention, described preset news category specifically can comprise: first category and the second classification;
Wherein, described first category can be the news category that attention rate is the highest under very first time scene, and described second classification can be the news category that attention rate is the highest under the second Novel Temporal Scenario.
In another kind of embodiment of the present invention, described preset news category can also comprise: the 3rd classification, and wherein, described 3rd classification is different with described second classification from described first category.
In another embodiment of the present invention, described first category specifically can comprise: current events classification, and described second classification specifically can comprise: personalization categories.
Described in another embodiment of the present invention, device is positioned at client, the refresh requests that described refresh requests can trigger for user, then described output module 505, can specifically for representing described targeted news to user.
In another kind of embodiment of the present invention, described device can be applied to server, and described refresh requests can be the refresh requests from client, described output module 505, can specifically for target resource described in client push.
For device embodiment, due to itself and embodiment of the method basic simlarity, so description is fairly simple, relevant part illustrates see the part of embodiment of the method.
Each embodiment in this instructions all adopts the mode of going forward one by one to describe, and what each embodiment stressed is the difference with other embodiments, between each embodiment identical similar part mutually see.
About the device in above-described embodiment, wherein the concrete mode of modules executable operations has been described in detail in about the embodiment of the method, will not elaborate explanation herein.
Fig. 6 is the block diagram of a kind of device 800 for news recommendation according to an exemplary embodiment.Such as, device 800 can be mobile phone, computing machine, digital broadcast terminal, messaging devices, game console, tablet device, Medical Devices, body-building equipment, personal digital assistant etc.
With reference to Fig. 6, device 800 can comprise following one or more assembly: processing components 802, storer 804, power supply module 806, multimedia groupware 808, audio-frequency assembly 810, the interface 812 of I/O (I/O), sensor module 814, and communications component 816.
The integrated operation of the usual control device 800 of processing components 802, such as with display, call, data communication, camera operation and record operate the operation be associated.Processing components 802 can comprise one or more processor 820 to perform instruction, to complete all or part of step of above-mentioned method.In addition, processing components 802 can comprise one or more module, and what be convenient between processing components 802 and other assemblies is mutual.Such as, processing element 802 can comprise multi-media module, mutual with what facilitate between multimedia groupware 808 and processing components 802.
Storer 804 is configured to store various types of data to be supported in the operation of equipment 800.The example of these data comprises for any application program of operation on device 800 or the instruction of method, contact data, telephone book data, message, picture, video etc.Storer 804 can be realized by the volatibility of any type or non-volatile memory device or their combination, as static RAM (SRAM), Electrically Erasable Read Only Memory (EEPROM), Erasable Programmable Read Only Memory EPROM (EPROM), programmable read only memory (PROM), ROM (read-only memory) (ROM), magnetic store, flash memory, disk or CD.
The various assemblies that power supply module 806 is device 800 provide electric power.Power supply module 806 can comprise power-supply management system, one or more power supply, and other and the assembly generating, manage and distribute electric power for device 800 and be associated.
Multimedia groupware 808 is included in the screen providing an output interface between described device 800 and user.In certain embodiments, screen can comprise liquid crystal display (LCD) and touch panel (TP).If screen comprises touch panel, screen may be implemented as touch-screen, to receive the input signal from user.Touch panel comprises one or more touch sensor with the gesture on sensing touch, slip and touch panel.Described touch sensor can the border of not only sensing touch or sliding action, but also detects the duration relevant to described touch or slide and pressure.In certain embodiments, multimedia groupware 808 comprises a front-facing camera and/or post-positioned pick-up head.When equipment 800 is in operator scheme, during as screening-mode or video mode, front-facing camera and/or post-positioned pick-up head can receive outside multi-medium data.Each front-facing camera and post-positioned pick-up head can be fixing optical lens systems or have focal length and optical zoom ability.
Audio-frequency assembly 810 is configured to export and/or input audio signal.Such as, audio-frequency assembly 810 comprises a microphone (MIC), and when device 800 is in operator scheme, during as call model, logging mode and speech recognition mode, microphone is configured to receive external audio signal.The sound signal received can be stored in storer 804 further or be sent via communications component 816.In certain embodiments, audio-frequency assembly 810 also comprises a loudspeaker, for output audio signal.
I/O interface 812 is for providing interface between processing components 802 and peripheral interface module, and above-mentioned peripheral interface module can be keyboard, some striking wheel, button etc.These buttons can include but not limited to: home button, volume button, start button and locking press button.
Sensor module 814 comprises one or more sensor, for providing the state estimation of various aspects for device 800.Such as, sensor module 814 can detect the opening/closing state of equipment 800, the relative positioning of assembly, such as described assembly is display and the keypad of device 800, the position of all right pick-up unit 800 of sensor module 814 or device 800 1 assemblies changes, the presence or absence that user contacts with device 800, the temperature variation of device 800 orientation or acceleration/deceleration and device 800.Sensor module 814 can comprise proximity transducer, be configured to without any physical contact time detect near the existence of object.Sensor module 814 can also comprise optical sensor, as CMOS or ccd image sensor, for using in imaging applications.In certain embodiments, this sensor module 814 can also comprise acceleration transducer, gyro sensor, Magnetic Sensor, pressure transducer or temperature sensor.
Communications component 816 is configured to the communication being convenient to wired or wireless mode between device 800 and other equipment.Device 800 can access the wireless network based on communication standard, as WiFi, 2G or 3G, or their combination.In one exemplary embodiment, communication component 816 receives from the broadcast singal of external broadcasting management system or broadcast related information via broadcast channel.In one exemplary embodiment, described communication component 816 also comprises near-field communication (NFC) module, to promote junction service.Such as, can based on radio-frequency (RF) identification (RFID) technology in NFC module, Infrared Data Association (IrDA) technology, ultra broadband (UWB) technology, bluetooth (BT) technology and other technologies realize.
In the exemplary embodiment, device 800 can be realized, for performing said method by one or more application specific integrated circuit (ASIC), digital signal processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD) (PLD), field programmable gate array (FPGA), controller, microcontroller, microprocessor or other electronic components.
In the exemplary embodiment, additionally provide a kind of non-transitory computer-readable recording medium comprising instruction, such as, comprise the storer 804 of instruction, above-mentioned instruction can perform said method by the processor 820 of device 800.Such as, described non-transitory computer-readable recording medium can be ROM, random access memory (RAM), CD-ROM, tape, floppy disk and optical data storage devices etc.
A kind of non-transitory computer-readable recording medium, when the instruction in described storage medium is performed by processor, make the device with processor can perform a kind of news recommend method, described method comprises: receive the refresh requests for news; The current time corresponding according to described refresh requests and/or the time interval between described refresh requests and a front refresh requests, determine the current time scene that described refresh requests is corresponding; Obtain the news category ratio that described current time scene is corresponding, select the news of corresponding news category as targeted news; Export described targeted news.
Fig. 7 is the structural representation of server in the embodiment of the present invention.This server 1900 can produce larger difference because of configuration or performance difference, one or more central processing units (centralprocessingunits can be comprised, CPU) 1922 (such as, one or more processors) and storer 1932, one or more store the storage medium 1930 (such as one or more mass memory units) of application program 1942 or data 1944.Wherein, storer 1932 and storage medium 1930 can be of short duration storages or store lastingly.The program being stored in storage medium 1930 can comprise one or more modules (diagram does not mark), and each module can comprise a series of command operatings in server.Further, central processing unit 1922 can be set to communicate with storage medium 1930, and server 1900 performs a series of command operatings in storage medium 1930.
Server 1900 can also comprise one or more power supplys 1926, one or more wired or wireless network interfaces 1950, one or more IO interface 1958, one or more keyboards 1956, and/or, one or more operating systems 1941, such as WindowsServerTM, MacOSXTM, UnixTM, LinuxTM, FreeBSDTM etc.
Those skilled in the art, at consideration instructions and after putting into practice invention disclosed herein, will easily expect other embodiment of the present invention.The present invention is intended to contain any modification of the present invention, purposes or adaptations, and these modification, purposes or adaptations are followed general principle of the present invention and comprised the undocumented common practise in the art of the disclosure or conventional techniques means.Instructions and embodiment are only regarded as exemplary, and true scope of the present invention and spirit are pointed out by claim below.
Should be understood that, the present invention is not limited to precision architecture described above and illustrated in the accompanying drawings, and can carry out various amendment and change not departing from its scope.Scope of the present invention is only limited by appended claim
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Above to a kind of news recommend method provided by the present invention, a kind of news recommendation apparatus and a kind of device recommended for news, be described in detail, apply specific case herein to set forth principle of the present invention and embodiment, the explanation of above embodiment just understands method of the present invention and core concept thereof for helping; Meanwhile, for one of ordinary skill in the art, according to thought of the present invention, all will change in specific embodiments and applications, in sum, this description should not be construed as limitation of the present invention.
Claims (14)
1. a news recommend method, is characterized in that, comprising:
Receive the refresh requests for news;
The current time corresponding according to described refresh requests and/or the time interval between described refresh requests and a front refresh requests, determine the current time scene that described refresh requests is corresponding;
Obtain the news category ratio that described current time scene is corresponding, select the news of corresponding news category as targeted news;
Export described targeted news.
2. method according to claim 1, is characterized in that, the step of the news category ratio that described acquisition described current time scene is corresponding, comprising:
According to described current time scene, search in the mapping relations between the preset time scene set up in advance and preset news category ratio, to obtain news category ratio corresponding to described current time scene; Wherein, described mapping relations are obtain according to the historical behavior data of user under preset time scene; Or
To the historical behavior data analysis of user under current time scene, to obtain news category ratio corresponding to described current time scene.
3. method according to claim 2, is characterized in that, sets up the mapping relations between preset time scene and preset news category ratio as follows:
To the historical behavior data analysis of user under preset time scene, to obtain user's attention rate for news category under above-mentioned preset time scene;
According to user for the attention rate of news category, determine the ratio between at least two kinds of preset news category, as the preset news category ratio that described preset time scene is corresponding.
4. method according to claim 1, it is characterized in that, the described current time corresponding according to described refresh requests and/or the time interval between described refresh requests and a front refresh requests, determine the step of the current time scene that described refresh requests is corresponding, comprising:
When the current time that described refresh requests is corresponding is positioned at very first time interval, current time scene corresponding for described refresh requests is defined as very first time scene; Or
When the current time that described refresh requests is corresponding is positioned at the second time interval, current time scene corresponding for described refresh requests is defined as the second Novel Temporal Scenario; Or
When the current time that described refresh requests is corresponding is positioned at the 3rd time interval and the described time interval exceeds interval threshold, current time scene corresponding for described refresh requests is defined as the 3rd Novel Temporal Scenario; Or
When the current time that described refresh requests is corresponding is positioned at the 3rd time interval and the described time interval does not exceed interval threshold, current time scene corresponding for described refresh requests is defined as the 4th Novel Temporal Scenario.
5., according to described method arbitrary in Claims 1-4, it is characterized in that, before the described targeted news of described output, described method also comprises:
Described targeted news is carried out interting sequence, to obtain sorted targeted news;
The then step of the described targeted news of described output, comprising: exported by sorted targeted news.
6. method according to claim 4, is characterized in that, described news category comprises: first category and the second classification;
Wherein, described first category is the news category that attention rate is the highest under very first time scene, and described second classification is the news category that attention rate is the highest under the second Novel Temporal Scenario.
7. method according to claim 6, is characterized in that, described news category also comprises: the 3rd classification, and wherein, described 3rd classification is different with described second classification from described first category.
8. the method according to claim 1 or 2 or 3 or 4 or 6 or 7, described method is applied to client, and described refresh requests is the refresh requests that user triggers, and the step of the described targeted news of described output, comprising:
Described targeted news is represented to user.
9. the method according to claim 1 or 2 or 3 or 4 or 6 or 7, described method is applied to server, and described refresh requests is the refresh requests from client, and the step of the described targeted news of described output, comprising:
To targeted news described in client push.
10. a news recommendation apparatus, is characterized in that, comprising:
Receiver module, for receiving the refresh requests for news;
Determination module, for according to current time corresponding to described refresh requests and/or the time interval between described refresh requests and a front refresh requests, determines the current time scene that described refresh requests is corresponding;
Acquisition module, for obtaining news category ratio corresponding to described current time scene;
Select module, for according to news category ratio corresponding to described current time scene, select the news of corresponding news category as targeted news; And
Output module, for exporting described targeted news.
11. 1 kinds of devices recommended for news, it is characterized in that, include storer, and one or more than one program, one of them or more than one program are stored in storer, and are configured to perform described more than one or one routine package containing the instruction for carrying out following operation by more than one or one processor:
Receive the refresh requests for news;
The current time corresponding according to described refresh requests and/or the time interval between described refresh requests and a front refresh requests, determine the current time scene that described refresh requests is corresponding;
Obtain the news category ratio that described current time scene is corresponding, select the news of corresponding news category as targeted news;
Export described targeted news.
12. devices according to claim 11, is characterized in that, described processor is also for performing described more than one or one routine package containing the instruction for carrying out following operation:
According to described current time scene, search in the mapping relations between the preset time scene set up in advance and preset news category ratio, to obtain news category ratio corresponding to described current time scene; Wherein, described mapping relations are obtain according to the historical behavior data of user under preset time scene; Or
To the historical behavior data analysis of user under current time scene, to obtain news category ratio corresponding to described current time scene.
13. devices according to claim 11, is characterized in that, described processor is also for performing described more than one or one routine package containing the instruction for carrying out following operation:
When the current time that described refresh requests is corresponding is positioned at very first time interval, current time scene corresponding for described refresh requests is defined as very first time scene; Or
When the current time that described refresh requests is corresponding is positioned at the second time interval, current time scene corresponding for described refresh requests is defined as the second Novel Temporal Scenario; Or
When the current time that described refresh requests is corresponding is positioned at the 3rd time interval and the described time interval exceeds interval threshold, current time scene corresponding for described refresh requests is defined as the 3rd Novel Temporal Scenario; Or
When the current time that described refresh requests is corresponding is positioned at the 3rd time interval and the described time interval does not exceed interval threshold, current time scene corresponding for described refresh requests is defined as the 4th Novel Temporal Scenario.
14., according to claim 11 to described device arbitrary in 13, is characterized in that, described processor is also for performing described more than one or one routine package containing the instruction for carrying out following operation:
Described targeted news is carried out interting sequence, to obtain sorted targeted news;
Sorted targeted news is exported.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510971864.2A CN105574182A (en) | 2015-12-22 | 2015-12-22 | News recommendation method and device as well as device for news recommendation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510971864.2A CN105574182A (en) | 2015-12-22 | 2015-12-22 | News recommendation method and device as well as device for news recommendation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105574182A true CN105574182A (en) | 2016-05-11 |
Family
ID=55884313
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510971864.2A Pending CN105574182A (en) | 2015-12-22 | 2015-12-22 | News recommendation method and device as well as device for news recommendation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105574182A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106570067A (en) * | 2016-10-12 | 2017-04-19 | 深圳市金立通信设备有限公司 | Terminal interface content display method and terminal |
| CN106789589A (en) * | 2017-01-03 | 2017-05-31 | 努比亚技术有限公司 | One kind shares processing method, device and terminal |
| CN106909658A (en) * | 2017-02-27 | 2017-06-30 | 百度在线网络技术（北京）有限公司 | Information flow recommends method, device and search engine |
| CN107193891A (en) * | 2017-05-02 | 2017-09-22 | 百度在线网络技术（北京）有限公司 | Content recommendation method and device |
| CN107436893A (en) * | 2016-05-26 | 2017-12-05 | 北京搜狗科技发展有限公司 | A kind of webpage recommending method and device |
| CN108810095A (en) * | 2018-05-18 | 2018-11-13 | 歌尔科技有限公司 | A kind of news push method and apparatus |
| CN109582898A (en) * | 2018-10-25 | 2019-04-05 | 北京奇虎科技有限公司 | A kind of generation method and device of the news web page page |
| CN109977305A (en) * | 2019-03-14 | 2019-07-05 | 努比亚技术有限公司 | Information processing method, mobile terminal and computer readable storage medium |
| CN110211590A (en) * | 2019-06-24 | 2019-09-06 | 新华智云科技有限公司 | A kind of processing method, device, terminal device and the storage medium of meeting hot spot |
| CN110851759A (en) * | 2019-10-31 | 2020-02-28 | 上海连尚网络科技有限公司 | Method and equipment for identifying gender of new user |
| CN111601164A (en) * | 2020-05-21 | 2020-08-28 | 广州欢网科技有限责任公司 | Intelligent television news pushing method and system |
| CN112912915A (en) * | 2020-03-31 | 2021-06-04 | 浙江核新同花顺网络信息股份有限公司 | Method and system for refreshing current page information |
| US11971934B2 (en) | 2020-03-31 | 2024-04-30 | Hithink Royalflush Information Network Co., Ltd. | Methods and systems for refreshing current page information |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102957742A (en) * | 2012-10-18 | 2013-03-06 | 北京天宇朗通通信设备股份有限公司 | Data pushing method and device |
| US20140032539A1 (en) * | 2012-01-10 | 2014-01-30 | Ut-Battelle Llc | Method and system to discover and recommend interesting documents |
| CN103686236A (en) * | 2013-11-19 | 2014-03-26 | 乐视致新电子科技（天津）有限公司 | Method and system for recommending video resource |
| CN104239587A (en) * | 2014-10-17 | 2014-12-24 | 北京字节跳动网络技术有限公司 | Method and device for refreshing news list |
| CN104469430A (en) * | 2014-12-24 | 2015-03-25 | 武汉泰迪智慧科技有限公司 | Video recommending method and system based on context and group combination |
| US20150324449A1 (en) * | 2011-03-30 | 2015-11-12 | Vcvc Iii Llc | Cluster-based identification of news stories |
-
2015
- 2015-12-22 CN CN201510971864.2A patent/CN105574182A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150324449A1 (en) * | 2011-03-30 | 2015-11-12 | Vcvc Iii Llc | Cluster-based identification of news stories |
| US20140032539A1 (en) * | 2012-01-10 | 2014-01-30 | Ut-Battelle Llc | Method and system to discover and recommend interesting documents |
| CN102957742A (en) * | 2012-10-18 | 2013-03-06 | 北京天宇朗通通信设备股份有限公司 | Data pushing method and device |
| CN103686236A (en) * | 2013-11-19 | 2014-03-26 | 乐视致新电子科技（天津）有限公司 | Method and system for recommending video resource |
| CN104239587A (en) * | 2014-10-17 | 2014-12-24 | 北京字节跳动网络技术有限公司 | Method and device for refreshing news list |
| CN104469430A (en) * | 2014-12-24 | 2015-03-25 | 武汉泰迪智慧科技有限公司 | Video recommending method and system based on context and group combination |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107436893A (en) * | 2016-05-26 | 2017-12-05 | 北京搜狗科技发展有限公司 | A kind of webpage recommending method and device |
| CN106570067A (en) * | 2016-10-12 | 2017-04-19 | 深圳市金立通信设备有限公司 | Terminal interface content display method and terminal |
| CN106789589A (en) * | 2017-01-03 | 2017-05-31 | 努比亚技术有限公司 | One kind shares processing method, device and terminal |
| CN106789589B (en) * | 2017-01-03 | 2020-02-14 | 努比亚技术有限公司 | Sharing processing method, sharing processing device and terminal |
| CN106909658A (en) * | 2017-02-27 | 2017-06-30 | 百度在线网络技术（北京）有限公司 | Information flow recommends method, device and search engine |
| CN107193891A (en) * | 2017-05-02 | 2017-09-22 | 百度在线网络技术（北京）有限公司 | Content recommendation method and device |
| CN108810095A (en) * | 2018-05-18 | 2018-11-13 | 歌尔科技有限公司 | A kind of news push method and apparatus |
| CN109582898A (en) * | 2018-10-25 | 2019-04-05 | 北京奇虎科技有限公司 | A kind of generation method and device of the news web page page |
| CN109977305B (en) * | 2019-03-14 | 2024-04-23 | 努比亚技术有限公司 | Information processing method, mobile terminal and computer readable storage medium |
| CN109977305A (en) * | 2019-03-14 | 2019-07-05 | 努比亚技术有限公司 | Information processing method, mobile terminal and computer readable storage medium |
| CN110211590A (en) * | 2019-06-24 | 2019-09-06 | 新华智云科技有限公司 | A kind of processing method, device, terminal device and the storage medium of meeting hot spot |
| CN110851759B (en) * | 2019-10-31 | 2022-11-29 | 上海连尚网络科技有限公司 | Method and equipment for identifying gender of new user |
| CN110851759A (en) * | 2019-10-31 | 2020-02-28 | 上海连尚网络科技有限公司 | Method and equipment for identifying gender of new user |
| CN112912915A (en) * | 2020-03-31 | 2021-06-04 | 浙江核新同花顺网络信息股份有限公司 | Method and system for refreshing current page information |
| US11971934B2 (en) | 2020-03-31 | 2024-04-30 | Hithink Royalflush Information Network Co., Ltd. | Methods and systems for refreshing current page information |
| CN111601164A (en) * | 2020-05-21 | 2020-08-28 | 广州欢网科技有限责任公司 | Intelligent television news pushing method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105574182A (en) | News recommendation method and device as well as device for news recommendation | |
| CN109299384B (en) | Scene recommendation method, device and system and storage medium | |
| US11409817B2 (en) | Display apparatus and method of controlling the same | |
| CN109118290B (en) | Method, system, and computer-readable non-transitory storage medium | |
| CN106164895B (en) | Methods, systems, and media for presenting suggestions of media content | |
| CN107656938B (en) | Recommendation method and device and recommendation device | |
| CN106874308B (en) | Recommendation method and device and recommendation device | |
| CN104954820A (en) | Program recommending method and device | |
| CN103944804B (en) | Contact recommending method and device | |
| CN109684507A (en) | Video recommendation method, video recommendations device and computer readable storage medium | |
| CN105630878A (en) | Method and apparatus for displaying application service information | |
| CN106331761A (en) | Live broadcast list display method and apparatuses | |
| CN107315487B (en) | Input processing method and device and electronic equipment | |
| CN106055707A (en) | Bullet screen display method and device | |
| CN110020148A (en) | A kind of information recommendation method, device and the device for information recommendation | |
| CN108227950A (en) | A kind of input method and device | |
| CN105373580A (en) | Method and device for displaying subjects | |
| CN111858971A (en) | Multimedia resource recommendation method, device, terminal and server | |
| CN106063231A (en) | Information transmission system, information reception method, device and system | |
| CN105447149A (en) | Interaction method, apparatus and electronic device for network searching | |
| CN104331503A (en) | Information push method and device | |
| CN104111979A (en) | Search recommendation method and device | |
| CN110322305A (en) | Data object information providing method, device and electronic equipment | |
| CN107622074A (en) | A kind of data processing method, device and computing device | |
| CN106202411A (en) | A kind of Search Results methods of exhibiting and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160511 |
|
| RJ01 | Rejection of invention patent application after publication |